© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 65939
    Prev
    Next
    INDEX
    Explanations

    processes over time

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    总裁
    -0.81
     sonno
    -0.78
    一行
    -0.76
    を生
    -0.76
     フラ
    -0.76
    rzu
    -0.75
    kepada
    -0.75
     expanded
    -0.72
    ersdorf
    -0.72
     sny
    -0.71
    POSITIVE LOGITS
     quickest
    1.63
     eventually
    1.53
     fastest
    1.49
     slowly
    1.49
     slowest
    1.47
     faster
    1.45
    eventually
    1.41
    slowly
    1.40
     Eventually
    1.38
     gradually
    1.38
    Activations Density 0.150%

    No Known Activations